Cascade Decoder: A Universal Decoding Method for Biomedical Image Segmentation
This work addresses a bottleneck in biomedical image segmentation for researchers and practitioners, though it appears incremental as it builds on existing encoder-decoder frameworks.
The paper tackles the under-exploration of decoders in encoder-decoder architectures for biomedical image segmentation by proposing a universal cascade decoder that improves accuracy, achieving considerable improvements on challenging tasks.
The Encoder-Decoder architecture is a main stream deep learning model for biomedical image segmentation. The encoder fully compresses the input and generates encoded features, and the decoder then produces dense predictions using encoded features. However, decoders are still under-explored in such architectures. In this paper, we comprehensively study the state-of-the-art Encoder-Decoder architectures, and propose a new universal decoder, called cascade decoder, to improve semantic segmentation accuracy. Our cascade decoder can be embedded into existing networks and trained altogether in an end-to-end fashion. The cascade decoder structure aims to conduct more effective decoding of hierarchically encoded features and is more compatible with common encoders than the known decoders. We replace the decoders of state-of-the-art models with our cascade decoder for several challenging biomedical image segmentation tasks, and the considerable improvements achieved demonstrate the efficacy of our new decoding method.